Related papers: Electra: Conditional Generative Model based Predic…

Research on deductive verification of probabilistic programs has considered expectation-based logics, where pre- and post-conditions are real-valued functions on states, and assertion-based logics, where pre- and post-conditions are boolean…

Retrieval-Augmented Generation (RAG) grounds language models in factual evidence but introduces critical challenges regarding knowledge conflicts between internalized parameters and retrieved information. However, existing reliability…

Commonsense knowledge is critical in human reading comprehension. While machine comprehension has made significant progress in recent years, the ability in handling commonsense knowledge remains limited. Synonyms are one of the most widely…

Performance analysis based on modelling consists of two major steps: model construction and model analysis. Formal modelling techniques significantly aid model construction but can exacerbate model analysis. In particular, here we consider…

Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available. Although existing studies have made some progress and can usually achieve…

Researchers and industry analysts are increasingly interested in computing aggregation queries over large, unstructured datasets with selective predicates that are computed using expensive deep neural networks (DNNs). As these DNNs are…

Large Language Models (LLMs) have demonstrated impressive performance in software engineering tasks. However, improving their accuracy in generating correct and reliable code remains challenging. Numerous prompt engineering techniques…

Achieving personalized alignment requires adapting large language models to each user's evolving context. While decoding-time personalization offers a scalable alternative to training-time methods, existing methods largely rely on implicit,…

Pre-trained masked language models have demonstrated remarkable ability as few-shot learners. In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA.…

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing among competing options, simply grounding generation in broadly…

We propose a novel approach for generating complex outputs that significantly improves accuracy in text-to-SQL tasks. Our method leverages execution results to select the most semantically consistent query from multiple candidates, enabling…

Long-form question answering (LFQA) aims to generate a paragraph-length answer for a given question. While current work on LFQA using large pre-trained model for generation are effective at producing fluent and somewhat relevant content,…

Fixing static analysis alerts in source code with Large Language Models (LLMs) is becoming increasingly popular. However, LLMs often hallucinate and perform poorly for complex and less common alerts. Retrieval-augmented generation (RAG)…

Hybrid Question-Answering (HQA), which targets reasoning over tables and passages linked from table cells, has witnessed significant research in recent years. A common challenge in HQA and other passage-table QA datasets is that it is…

The intelligent question answering (IQA) system can accurately capture users' search intention by understanding the natural language questions, searching relevant content efficiently from a massive knowledge-base, and returning the answer…

Standard quantum inference converts quantum data into classical outputs. We study an alternative inference setting in which the desired output is quantum, preserving coherence. Such settings include quantum purity amplification (QPA),…

Prompting methods for language models, such as Chain-of-thought (CoT), present intuitive step-by-step processes for problem solving. These methodologies aim to equip models with a better understanding of the correct procedures for…

Explainable recommendation is a technique that combines prediction and generation tasks to produce more persuasive results. Among these tasks, textual generation demands large amounts of data to achieve satisfactory accuracy. However,…

Pre-trained large-scale vision-language models (VLMs) have acquired profound understanding of general visual concepts. Recent advancements in efficient transfer learning (ETL) have shown remarkable success in fine-tuning VLMs within the…

In this paper, we focus on task-specific question answering (QA). To this end, we introduce a method for generating exhaustive and high-quality training data, which allows us to train compact (e.g., run on a mobile device), task-specific QA…